Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Training on Custom Data #37

Open
DecentMakeover opened this issue Aug 1, 2019 · 5 comments
Open

Training on Custom Data #37

DecentMakeover opened this issue Aug 1, 2019 · 5 comments

Comments

@DecentMakeover
Copy link

Hi , Thanks for sharing your work, Could you please post an some guidelines/steps to train on custom data?

Thanks

@thekeviv
Copy link

thekeviv commented Aug 5, 2019

Yes, I am also struggling to make this work on my own dataset

@AndrejHafner
Copy link

Did you have any success training on your own data?

@DecentMakeover
Copy link
Author

ended up using this, https://github.com/CSAILVision/semantic-segmentation-pytorch. This has a HRNet Backbone support.

@InternetMaster1
Copy link

InternetMaster1 commented May 26, 2020

@sunke123

How to do training from scratch on a custom dataset (with base model without any pretraining on CityScapes or any other dataset) with this library for HRNETV2-Small-W18?

I was hoping I don't have to use a separate library to achieve this.

Thanks!

@ghost
Copy link

ghost commented Aug 8, 2020

@InternetMaster1

If you are using this file, then it doesn't need any pretrained network. Every time you run the code, it runs from scratch.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants